Abstract: A device may generate a product delivery map that includes route information that is to be used by a fleet of delivery vehicles for performing a set of deliveries, and a set of location constraints identifying locations that are to be avoided by the fleet of delivery vehicles when performing the set of deliveries. The device may generate a collaborative interactions map that includes a set of collaborative constraints indicating particular supplier organizations that are candidates to engage in collaborative logistics. The device may determine, based on the set of location constraints and the set of collaborative constraints, a set of delivery schedules that are to be used to perform the set of deliveries. The device may provide the set of delivery schedules to one or more devices associated with the delivery organization to allow the fleet of delivery vehicles to perform the set of deliveries.

Abstract: A system maintains a knowledge layout to support the building of event and analytics models in parity. The system uses the event models to provide a snapshot of the relevant conditions present when a challenge event occurs. The system uses the analytics models to select one or more actions (which may include robotic tasks) to respond to the challenge condition. In some cases, the system may render continued response compulsory until a successful response to the challenge event is achieved.

Abstract: A vehicle driver monitoring system and method for capturing driver performance parameters is disclosed. The vehicle driver monitoring system and method uses multiple data sources to capture driver performance parameters. Data from one source can be used to validate data from another data source. Additionally, the data from one data source can be used to compensate for missing or corrupt data from the other data source. The vehicle driver monitoring system and method uses a mobile app on a mobile device that can automatically sense when a registered driver is in the vehicle with the mobile device, which helps the vehicle driver monitoring system verify that captured performance parameters are related to the registered driver driving the vehicle. The mobile app can also communicate with the driver in real time.

Abstract: An interactive troubleshooting assistant and method for troubleshooting a system in real time to repair (fix) one or more problems in a system is disclosed. The interactive troubleshooting assistant and method may include receiving multimodal inputs from sensors, wearable devices, a person, etc. that may be input into a feature extractor including attention layers and pre-processing units of a cloud computing system hosted by one or more servers, such as a private cloud system. A pre-processing unit converts the raw multimodal input into a structed form so that an attention layer can give weights to features provided by the pre-processing unit according to their importance. The weighted extracted features may be provided to an actions predictor. The actions predictor generates the most suitable action based on the weighted extracted features generated by the feature extractor based on the multimodal inputs.

Abstract: A system and method to intelligently formulate automation strategies for technology infrastructure operations are disclosed. The system and method include analyzing infrastructure issue data from support tickets and predicting automation solutions. A cost-benefit analysis is then performed on the automation solutions. Solutions can be ranked and recommended according to the cost-benefit analysis.

Abstract: A system and method to balance computational loads across multiple computing systems, such as servers in a server cluster, is disclosed. The system includes a load balancer. Upon receiving a new computing request corresponding to an expected throughout, the load balancer identifies a computing system that is most likely to fail and sends the new computing request to a different computing system. The load balancer uses a mutational algorithm to identify potentially problematic throughputs for a given computing system in a given state. The mutational algorithm is used to determine latency-throughput curves that are fit to a data population that includes many diverse data points with relatively high slopes in a 2D latency-throughput space.

Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, for location-based content delivery to vehicles using LiFi is disclosed. In one aspect, a method is disclosed that includes operations of obtaining, by a LiFi transceiver unit, a vehicle identifier that identifies a vehicle, providing, by the LiFi transceiver unit and to a server, the vehicle identifier using an internet protocol network, wherein the server is configured to determine a location of the vehicle based on the vehicle identifier and an identity of the LiFi transceiver unit that provided the vehicle identifier, receiving, by the LiFi transceiver unit and from the server, the location of the vehicle and location-based content, encoding, by the LiFi transceiver unit, the location-based content into multiple light signals, and providing, by the LiFi transceiver unit, the encoded location-based content to the vehicle using the location of the vehicle.

Abstract: A device receives image data that depicts an individual, identifies the individual by using a target recognition technique to analyze the image data, and identifies human attributes of the individual. The device determines a risk level that represents a likelihood of the individual being or becoming involved in a harmful act. The risk level may be determined by using the human attributes as part of a machine-learning-driven emotional analysis of the individual. The device provides a message, selected based on whether the risk level satisfies at least one of the one or more threshold risk levels, to another device, to cause the other device to perform actions that are indicative of the risk level being associated with a low amount of risk, or other actions indicative of the risk level being associated with a high amount of risk and that are associated with assisting in prevention of the harmful act.

Abstract: A participant node of a distributed ledger network may detect a tool event token stored on a blockchain. The tool event token may be generated by another participant node of the distributed ledger network. The tool event token may represent execution of a devops tool in a toolchain for an integrated devops environment. The participant node may generate, in response to detection of the tool event token, a new tool path. The participant node may aggregate the new tool path with a previously generated tool path. The optimization node may execute a fitness logic to generate a fitness metric based the aggregated path. The optimization node may prioritize the aggregated tool path with other unique tool paths. The optimization node may select an optimal tool path and communicate an instruction to configure the integrated devops environment with devops tools identified in the optimal tool path.

Abstract: An idea recognition tool utilizes natural language processing techniques to capture, understand, and identify ideas that are mentioned by speakers during a conversation involving multiple speakers, and tag ideas attributed to their speaker accordingly. The idea recognition tool also autonomously triggers search operations to obtain supplemental information for enriching the underlying identified ideas. The identified ideas and supplemental information are grouped, classified, and formatted into a dedicated format for further analysis, as well as considered for implementing relevant actions.

Abstract: Identifying a vehicle in a toll system includes accessing image data for a first vehicle and obtaining license plate data from the accessed image data for the first vehicle. A set of records is accessed. Each record includes license plate data for a vehicle. The license plate data for the first vehicle is compared with the license plate data for vehicles in the set of records. Based on the results of the comparison of the license plate data, a set of vehicles is identified from the vehicles having records in the set of records. Vehicle fingerprint data is accessed for the first vehicle. The vehicle fingerprint data for the first vehicle is based on the image data for the first vehicle. Vehicle fingerprint data for a vehicle in the set of vehicles is accessed. Using a processing device, the vehicle fingerprint data for the first vehicle is compared with the vehicle fingerprint data for the vehicle in the set of vehicles.

Abstract: A device receives a command to identify an automation evaluation for a role, determines tasks of the role based on data relating to the role, and determines activities for the tasks based on the data relating to the role. The device determines one or more automation scores, which correspond to a suitability for automation of the activities, based on a set of characteristics of the activities and based on the data relating to the role. The automation scores are determined using a machine learning model to parse natural language descriptions of the activities and score parsed portions of the natural language descriptions. The device generates, for the role, an aggregate automation score based on the automation scores, determines the automation evaluation for the role based on the aggregate automation score and characteristics of an entity associated with the role, and performs an action relating to the automation evaluation.

Abstract: Apparatus and methods for solving global optimization tasks using quantum computing. In one aspect, a method includes receiving input data, the input data comprising (i) data representing one or more local solutions to the global optimization task, and (ii) data representing one or more task objectives; mapping the received input data to a quantum domain; performing a genetic algorithm on the mapped input data using the quantum computing device to obtain a solution to the global optimization task in the quantum domain; and obtaining a solution to the global optimization task in a classical domain by mapping the obtained solution to the global optimization task in the quantum domain to the classical domain.

Abstract: Implementations include receiving, by a DDT platform, computer-readable files including test data, the test data including data to execute at least one transaction during testing of a software system that is at least partially hosted by a vendor back-end system, the software system being configured for customer use, providing, by the DDT platform, one or more test scenarios for execution by the software system on the vendor back-end system, the one or more test scenarios including a set of activities to conduct transactions by the software system using at least a portion of the test data, scheduling, by a scheduler of the DDT platform, execution of the one or more test scenarios using a test harness of the DDT platform, receiving, by the DDT platform, test results from the vendor back-end system, and comparing, by the DDT platform, the test results to expected results to provide a comparison as output.

Abstract: An optimized test data selection strategy references a sampling file that identifies data attributes that serve as the basis of the test data selection strategy. By analyzing fields and the corresponding field values of the sample imprint, a total number of test data selected for inclusion into a sample dataset is reduced. The test data selection strategy provides an efficient methodology for implementing a data comparison testing process.

Abstract: A method for provisioning a computer includes providing a graph that defines relationships between one or more hardware components of a plurality of computers and component characteristics of the one or more hardware components, and relationships between one or more applications and requirements of the one or more applications. The method further includes receiving a selection of an application and determining, via the graph, whether at least one computer with hardware components capable of meeting the requirements of the application exists. If a computer exits, the method also includes communicating the application to the computer; triggering the computer to execute the application; and communicating, from the computer, data processed by the application to an external system.

Abstract: A device may receive input indicating one or more search parameters associated with a search. The device may perform a comparison of the input and a dictionary file to identify the one or more search parameters associated with the search. The dictionary file may be associated with a domain specific language. The device may determine a combination or quantity of search parameters associated with the search based on a result of the comparison. The device may select a search template to be used to perform the search based on the combination or quantity of search parameters. The search template may be populated with information identifying the one or more search parameters. The device may perform the search using the search template populated with the information identifying the one or more search parameters. The device may perform an action based on a result of performing the search.

Abstract: A system and method for intelligently and automatically generating deployable code for target platforms and frameworks based on images or other graphical inputs is disclosed. The system and method leverage artificial intelligence to automatically identify and classify elements of a design as feature patterns. Identification is performed using convolutional neural networks, while classification is done using a Softmax classifier. The intelligent system can then automatically generate code for target platforms and frameworks that reproduce the feature patterns. Target platforms may include web platforms, mobile platforms (such as mobile phones), wearable platforms (such as smart watches), and extended reality platforms (which includes augmented reality (AR), virtual reality (VR), and/or combinations of AR/VR).

Abstract: A device may receive first data associated with a set of systems used to implement a process. The device may determine a system topology for the set of systems. The device may identify a set of control points associated with the set of systems. The set of control points may include a set of points in the system topology where second data is received or provided by the set of systems. The second data may include information to be used by the set of systems during the process. The device may identify a set of values for a set of metrics related to the set of systems. The set of values may be identified based on the first data. The device may identify an error related to the set of control points or the set of metrics. The device may perform an action to facilitate fixing of the error.

Abstract: A multi-layer resource control stack based system may generate an availability indication for multiple domains supported by the resource control stack and send the indication to a client node. The client node may respond with a selection of a domain. The client node may also indicate a compute resource to be managed by the resource control stack. In response to the selection from the client node, the resource control stack may initiate a virtual representation of the domain. The client node may interact with the virtual representation to receive recommendations, utilization data, and control information relevant to the compute resource and within a subject area associated with the domain.